---
base_model:
- nbeerbower/mistral-nemo-gutenberg-12B-v2
- nbeerbower/SmolNemo-12B-FFT-experimental
- nbeerbower/Mistral-Nemo-Moderne-12B-FFT-experimental
- nbeerbower/Mistral-Nemo-Prism-12B-v2
library_name: transformers
tags:
- mergekit
- merge

---
# Nemo-Loony-12B-experimental

This is a merge of pre-trained language models created using [mergekit](https://github.com/cg123/mergekit).

## Merge Details
### Merge Method

This model was merged using the [TIES](https://arxiv.org/abs/2306.01708) merge method using [nbeerbower/mistral-nemo-gutenberg-12B-v2](https://huggingface.co/nbeerbower/mistral-nemo-gutenberg-12B-v2) as a base.

### Models Merged

The following models were included in the merge:
* [nbeerbower/SmolNemo-12B-FFT-experimental](https://huggingface.co/nbeerbower/SmolNemo-12B-FFT-experimental)
* [nbeerbower/Mistral-Nemo-Moderne-12B-FFT-experimental](https://huggingface.co/nbeerbower/Mistral-Nemo-Moderne-12B-FFT-experimental)
* [nbeerbower/Mistral-Nemo-Prism-12B-v2](https://huggingface.co/nbeerbower/Mistral-Nemo-Prism-12B-v2)

### Configuration

The following YAML configuration was used to produce this model:

```yaml
models:
  - model: nbeerbower/Mistral-Nemo-Moderne-12B-FFT-experimental
    parameters:
      weight: 1
  - model: nbeerbower/SmolNemo-12B-FFT-experimental
    parameters:
      weight: 1
  - model: nbeerbower/Mistral-Nemo-Prism-12B-v2
    parameters:
      weight: 1
merge_method: ties
base_model: nbeerbower/mistral-nemo-gutenberg-12B-v2
parameters:
  normalize: true
  int8_mask: true
dtype: bfloat16


```